Software Engineer, Agent Evaluation and Quality
Cursor (Anysphere) · San Francisco; New York
Job information is sourced from publicly available employer career pages. Always verify details on the employer's official website before applying.
Why this job?
Discovery score 42/100, built only from evidence stored with this listing.
- New official employer listing
Score components
- Recency (moves as the posting ages)+18
- Official employer source+15
- Rare role+1
- Company source health+8
Not present on this posting: Salary disclosed、Remote position、Visa sponsorship mentioned、Relocation mentioned、Not found on monitored job boards.
Reasons come from the employer's own posting and our verified source checks. Nothing here is inferred beyond those stored signals.
Job description
Our mission is to automate coding. The first step in our journey is to build the best tool for professional programmers, using a combination of inventive research, design, and engineering. Our organization is very flat, and our team is small and talent dense. We particularly like people who are truth-seeking, passionate, and creative. We enjoy spirited debate, crazy ideas, and shipping code.
Responsibilities
As a Software Engineer on the Agent Quality team at SpaceXAI, you’ll build the measurement, evaluation, and feedback-loop infrastructure that makes the Cursor core agent reliably better over time. This role sits at the intersection of product, data, and engineering: you’ll instrument what matters, help define how we judge quality, build pipelines and tooling to analyze agent behavior at scale, and partner closely with research, product, and infrastructure teams to turn insights into improvements. Your impact will compound across every Cursor product built on the shared harness—and across high-stakes decisions around model choice, quality, and cost. What you’ll work on • Designing and building best-in-class AI evaluation system: curated datasets, offline replay, scorers / judges, regression alerts, and dashboards.
• Designing feedback loops from real usage: collecting, cleaning, and interpreting user signals to inform model and harness changes.
• Developing analysis tooling and workflows for debugging agent behavior: deep dives on failure modes, clustering themes, and surfacing actionable insights.
• Improving reliability and guardrails by making quality measurable and operational: defining “good/bad/degraded” sessions, alerting, and triage primitives.
You may be a fit if • You’ve built and operated evaluation or measurement systems, such as AI evals, experimentation, ranking/relevance, or search quality. You can turn ambiguous “quality” questions into concrete metrics, pipelines, and decisions.
• You have strong data acumen, and can collaborate effectively with data scientists and researchers.
• You have taste and strong opinions on model and agent behaviors. You stay up-to-date and informed on emerging research and industry trends.
• You have strong software engineering fundamentals and enjoy shipping production systems.
Applying If there appears to be a fit, we'll reach to schedule 2-3 short technicals. After, we'll schedule an onsite in our office, where you'll work on a small project, discuss ideas, and meet the team. #LI-DNI